diff --git a/recipes/deepseek-v4-1-flash-on-4x-dgx-spark-tuned-tp4-sglang-dspark/recipe.yaml b/recipes/deepseek-v4-1-flash-on-4x-dgx-spark-tuned-tp4-sglang-dspark/recipe.yaml
index db385f00d..4082d82b3 100644
--- a/recipes/deepseek-v4-1-flash-on-4x-dgx-spark-tuned-tp4-sglang-dspark/recipe.yaml
+++ b/recipes/deepseek-v4-1-flash-on-4x-dgx-spark-tuned-tp4-sglang-dspark/recipe.yaml
@@ -293,3 +293,5 @@ provenance:
     - 'https://github.com/knapcio/DeepSeek-V4.1-Flash-4x-DGX-Spark-TP4/blob/main/docs/results/validation-20260929-v23.txt'
     - 'https://github.com/knapcio/DeepSeek-V4.1-Flash-4x-DGX-Spark-TP4/blob/main/docs/upstream-watch.md'
   notes: "Submitted 2026-10-10 from lar-scout ingest card t_ad3aebd3. Repo @ fa1356384ed246f3040775210668f02a1bba3426 (HEAD verified via git ls-remote 2026-10-10; AGPL-3.0-or-later, upstream README preserved at docs/README-upstream.md with the credit chain kept verbatim). Launch argv transcribed from boot.py serve() + .env.tp4.example EXTRA_SGLANG_ARGS at that sha and flag-verified against boot.py's own env plumbing (spec/DSPARK/tables/nnodes/max-total-tokens/EXTRA_SGLANG_ARGS passthrough; EP_SIZE=1 pairs with DSV41_MOE_B12X_NEXT per .env.tp4.example comment; --min-free-slots-delay 1 matches README; DSPARK_SPS_TABLE=/state/dspark_sps.json only applied when the file exists). Performance rows transcribed from the repo's own bench docs (README 'Current results' + docs/results/validation-20260929-v23.txt sparkDash section) — measured, not claimed-by-anecdote; all at the 2200 MHz SM clock cap on a switched RoCE fabric (switchless ring slower, see notes). Engine pins from Dockerfile.canary-roce + scripts/fetch-sglang-canary.sh + runtime/b12x_next/b12x_next/SOURCE_COMMIT at the same sha; MiaAI upstream HEAD pinned via git ls-remote same day. HARDWARE NOTE: dgx-spark-x4 is a NEW device_count profile (site had 1x only) — hardware_profiles row seeded by a 0041-convention INSERT-only migration (family dgx-spark, generation blackwell, 128 GB unified memory each) submitted alongside this ingest, mirroring the 0053 cmp-170hx-x1 and 0047 rtx-3090-x4 precedents so the ingest resolves the seed slug instead of silent-creating a NULL card_family orphan bucket."
+max_context_len: 1048576
+kv_pool_tokens: 3670000